Stochastic Dynamics of Neural Networks
- 1 January 1986
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics
- Vol. 16 (1) , 73-83
- https://doi.org/10.1109/tsmc.1986.289283
Abstract
The dynamics of stochastic neural networks are presented. The model is an algorithm based upon the assumption that the activities of neurons are asynchronous. It is proven that networks with fixed synaptic efficacies cannot sustain oscillating activities. Following Choi and Huberman, the dynamics of instantaneous frequencies is derived. The equations are solved for associative and for recursive networks by introducing order parameters coupled to stored patterns. It is shown that the networks relax towards one of the stored configurations in a matter of a few refractory periods, whatever the size of the network. The relaxation time diverges in recursive networks at a critical noise Bc, above which no stored pattern can be retrieved. These results have been confirmed using computer simulations.Keywords
This publication has 27 references indexed in Scilit:
- A Boolean complete neural model of adaptive behaviorBiological Cybernetics, 1983
- Digital dynamics and the simulation of magnetic systemsPhysical Review B, 1983
- Ergodicity of the Coupling Constants and the Symmetric-Replicas Trick for a Class of Mean-Field Spin-Glass ModelsPhysical Review Letters, 1983
- Broken ergodicityAdvances in Physics, 1982
- Classical Spin-Glass ModelPhysical Review Letters, 1982
- A neural model for category learningBiological Cybernetics, 1982
- Memory, Learning, and Higher FunctionPublished by Springer Nature ,1982
- Pattern formation, contrast control, and oscillations in the short term memory of shunting on-center off-surround networksBiological Cybernetics, 1975
- Large-scale activity in neural nets II: A model for the brainstem respiratory oscillatorBiological Cybernetics, 1975
- Associatron-A Model of Associative MemoryIEEE Transactions on Systems, Man, and Cybernetics, 1972